© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13640
    Prev
    Next
    INDEX
    Explanations

    variations in the structure or patterns of code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſicht
    -1.08
    featureID
    -1.06
    OGND
    -1.05
    ſchaft
    -1.05
    MLLoader
    -1.03
    ſſung
    -1.02
    niſſe
    -1.02
    iſchen
    -1.00
    RenderAtEndOf
    -0.98
     الحره
    -0.97
    POSITIVE LOGITS
    0
    0.62
    1
    0.48
    [toxicity=0]
    0.46
    I
    0.43
    ↵
    0.42
    2
    0.41
    ，
    0.40
    But
    0.38
    When
    0.38
     But
    0.35
    Activations Density 0.980%

    No Known Activations